Add OCI Data Science Model Deployment Embedding Integration

[mrDzurb]

Description

Oracle Cloud Infrastructure (OCI) Data Science is a fully managed, serverless platform for data science teams to build, train, and manage machine learning models in Oracle Cloud Infrastructure. his PR introduces a new embedding integration with Oracle Cloud Infrastructure (OCI) Data Science Model Deployment endpoints. The integration allows generating text embeddings asynchronously or synchronously, leveraging the OCI Signer for authentication.

llama_index_test_base.pdf

New Package?

Did I fill in the tool.llamahub section in the pyproject.toml and provide a detailed README.md for my new integration or package?

• Yes
• No

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

• Yes
• No

Type of Change

Please delete options that are not relevant.

• New feature (non-breaking change which adds functionality)
• This change requires a documentation update

How Has This Been Tested?

• I performed thorough manual testing
• I added new unit tests to cover this change
• I believe this change is already covered by existing unit tests

Suggested Checklist:

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added Google Colab support for the newly added notebooks.
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I ran make format; make lint to appease the lint gods

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[mrDzurb]

Hi @logan-markewich,

I wanted to kindly ask for your help with the review of this PR. The changes introduce integration for invoking Embedding models on OCI Data Science, and I’d greatly appreciate your feedback and insights.

Additionally, I’ve encountered an issue with failing tests during the CI pipeline due to the absence of the oracle-ads library, despite it being listed in the pyproject.toml file. All the tests pass locally without any problems. It seems the oracle-ads library is not being installed in the CI environment before running the tests. It looks like that poetry doesn't take into account the pyproject.toml dependencies.

When you have time, could you please take a look at this and share your thoughts on what might be causing this discrepancy? Your guidance would be incredibly helpful.

Thank you in advance for your time and support!

[logan-markewich]

@mrDzurb seems like pants doesn't want to install this. I think our CICD is missing some system level dependency. Might take some time to figure out whats going on

[mrDzurb]

Hi @logan-markewich, thanks for taking a look on this.
It seems that adding the following rule to the BUILD file resolved the test failures for Python 3.9:

poetry_requirements(
    name="poetry",
    module_mapping={"oracle-ads": ["ads"]},
)

However, the tests for Python 3.10, 3.11, and 3.12 are still failing, but for a different reason. Maybe just restarting the tests will help. The logs don't give any clues what is failing.

[logan-markewich]

pants is hiding the true error it seems -- probably some system level issue, or an issue with some tricky dependency that needs a particular c compiler or something. Maybe I'll just disable tests for all but python 3.9